Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.
Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.
Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.
Split the diffs viewer Shiki language pack into an external publishable plugin.
The diffs plugin keeps the default curated syntax set, while the new @openclaw/diffs-language-pack package carries the extended Shiki languages for npm and ClawHub distribution. The install metadata includes the external ClawHub spec, and the curated C# alias set keeps both c# and cs supported without the language pack.
Co-authored-by: Dallin Romney <dallinromney@gmail.com>
Fix non-interactive and wizard onboarding reruns so existing agent lists and bindings are preserved unless the user explicitly resets config.
Isolate legacy `plugins.installs` migration into its own write so the config size-drop allowance cannot mask unrelated config loss, while preserving new or repaired install records for the final plugin-index commit. Also keep shrinkwrap generation pinned to pnpm-locked transitive patch versions only when the dependency edge still allows that version, and isolate the tooling Vitest shard that mutates process state.
Fixes#84692.
Replaces #84748.
Co-authored-by: yetval <yetvald@gmail.com>
Suppress reasoning-prefixed silent replies before outbound delivery while preserving substantive replies that merely end with the silent token.\n\nFixes #66701.\n\nThanks @zuoanCo for the PR and @Cavadus for the report.\n\nProof: focused Vitest and pnpm check:changed passed on Testbox-through-Crabbox tbx_01ksmvfw0gk9xwh10ra1cyhzfw; CI passed for head a014eb0d91.
Fixes#87226.
Preserve the already-applied `openai` to `openai-codex` Codex runtime promotion when the persisted selection is canonical `openai` with the same model, while keeping explicit runtime provider changes switchable.
Verification:
- `node scripts/run-vitest.mjs src/agents/live-model-switch.test.ts`
- `/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- `pnpm check:changed` via Testbox `tbx_01ksmr59zdaqj3617w8w53xv4t` / Actions run `26512418770`
- Real behavior proof override gate: Actions run `26513059970`
Co-authored-by: Peter Lindsey <peter@lindsey.jp>
Keeps plain `openclaw status` on a bounded fast path while preserving local status metadata. The default text scan now avoids network update fetches, live channel checks, setup fallback work, and unbounded session hydration; deep/all status keeps the fuller behavior.
Behavior addressed: default status latency from update, channel, setup, and session scans
Real environment tested: GitHub Actions on PR head 98f589a35df74a7abb8327984d0103bb9f31af3e; local focused lint; autoreview
Exact steps or command run after this patch: CI workflow 26510790999; CodeQL workflow 26510790924; CodeQL Critical Quality workflow 26510791058; OpenGrep workflow 26510791138; autoreview branch against origin/main
Evidence after fix: all current-SHA workflows completed successfully; autoreview clean; local focused core oxlint passed on touched status files
Observed result after fix: default status hydrates only visible recent sessions, keeps local update metadata, and shows intentionally skipped SecretRef credentials as unknown instead of warning
What was not tested: live provider/channel roundtrip
Co-authored-by: 1052326311 <1052326311@users.noreply.github.com>
Route Telegram sendMessage action replies through durable outbound delivery so completed agent responses remain retryable when the gateway send path times out.
Verified with focused Telegram/outbound tests, extension test typecheck, prepare build/check/full test gates, and green CI rerun for head 20b45687e1.
Move vLLM Qwen thinking control onto configured model compat metadata and carry it through catalog/model-selection/runtime thinking contexts.
Also migrate legacy provider/default request params in doctor and keep Pi/runtime model rows buildable with explicit reasoning defaults.
Thanks @rendrag-git.
Co-authored-by: rendrag-git <253747599+rendrag-git@users.noreply.github.com>
Summary:
- The PR moves the runtime `HEARTBEAT.md` bootstrap template into `src/agents/templates`, keeps docs templates ... or other workspace files, adds a legacy heartbeat-template doctor repair, and updates package guards/tests.
- PR surface: Source +281, Tests +283, Docs +11, Config +1, Other 0. Total +576 across 15 files.
- Reproducibility: yes. from source inspection: current main loads `HEARTBEAT.md` from the docs template, and ... pty heartbeat file non-empty to the runtime. I did not run a live heartbeat repro in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(doctor): recognize heartbeat docs boilerplate
- PR branch already contained follow-up commit before automerge: fix(agents): update heartbeat workspace test
- PR branch already contained follow-up commit before automerge: fix(doctor): tighten heartbeat template repair
Validation:
- ClawSweeper review passed for head e34e85864c.
- Required merge gates passed before the squash merge.
Prepared head SHA: e34e85864c
Review: https://github.com/openclaw/openclaw/pull/85416#issuecomment-4519851630
Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Carry over #82973 and fix#81281 by preserving explicit cacheRetention for OpenAI-compatible completions providers that opt into prompt-cache-key support.
The change keeps explicit cacheRetention suppressed for OpenAI-compatible providers without compat.supportsPromptCacheKey, adds regression coverage for both paths, and updates prompt-caching docs for prompt_cache_key / prompt_cache_retention behavior.
Fixes#81281.
Supersedes #82973.
Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
Fix runtime context placement so hidden runtime context is model-visible before the active user turn without persisting as a visible/session message.
Verification:
- git diff --check origin/main...origin/pr/86995-merge
- gh pr checks 86995 --repo openclaw/openclaw --watch=false
- gh run rerun 26493979156 --repo openclaw/openclaw --failed
- gh run watch 26493979156 --repo openclaw/openclaw --exit-status
- CodeQL run 26493979156 attempt 2, Security High (mcp-process-tool-boundary) job 78066719467 passed
Preserve replayability for direct Anthropic sessions whose stored assistant thinking blocks have empty or blank signatures after a newer user turn. Older invalid thinking-only assistant turns are replaced with the existing omitted-reasoning placeholder so the turn shape survives provider replay.
Also keep active tool-use continuations safe: when an assistant tool call is followed by tool results, preserve the latest assistant thinking block so signed-thinking providers can replay the current tool turn unchanged.
Proof:
- node scripts/run-vitest.mjs src/agents/pi-embedded-runner.sanitize-session-history.test.ts src/agents/pi-embedded-runner/thinking.test.ts test/scripts/openclaw-e2e-instance.test.ts
- pnpm check:changed via Blacksmith Testbox through Crabbox, tbx_01ksmfypqet50et92vdm5mmv5v, run https://github.com/openclaw/openclaw/actions/runs/26505947008
- Live Anthropic Messages replay accepted the OpenClaw-sanitized active tool-turn history with a real thinking signature.
- PR CI on 37c2e72d82 completed successfully for relevant checks.
Fixes#86886.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Forward cache-read token counts through the OpenAI-compatible chat-completions usage shape as prompt_tokens_details.cached_tokens so clients can price cached turns correctly.
Align internal gateway usage typing with the expanded wire shape.
Thanks @caz0075.
Preserve existing `agents.list` and top-level `bindings` during ordinary onboarding reruns so rerunning `openclaw onboard` cannot silently wipe configured agents or routing bindings.
Keep config size-drop allowances scoped to explicit reset/import/plugin-install migration flows, validate binding agent ids with normalized agent ids, and add doctor repair coverage for dangling bindings that is still best-effort around malformed agent lists.
Closes#84692.
Co-authored-by: yetval <yetvald@gmail.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Closes#87181.
Direct Anthropic Messages requests now send bare Claude model ids even when OpenClaw stores them with the `anthropic/` provider prefix. Anthropic-compatible proxy and custom endpoint routes keep slash-bearing model ids unchanged so configured proxy models do not regress.
Also preserves the original parse error as `cause` in the JSONL request tail helper to keep the current CI lint gate green.
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
